Extracting sequence features to predict protein-DNA interactions: a comparative study.
Extracting sequence features to predict protein-DNA interactions: a comparative study.
复制标题
提取序列特征以预测蛋白质-DNA相互作用：比较研究。
DOI：
10.1093/nar/gkn361
复制
发表时间：
2008-07
影响因子：
14.9
通讯作者：
Liu, Jun S.
中科院分区：
文献类型：
--
作者：
Zhou, Qing;Liu, Jun S.
预测蛋白质，特别是转录因子（TF）如何以及在何处与DNA相互作用是生物学中的一个重要问题。我们在这里提出了一个系统的研究预测建模方法的TF-DNA结合问题，这已被频繁地证明是更有效的比那些方法只基于特定位置的权重矩阵（PWMs）。在这些方法中，通过回归框架推断基因组序列与基因表达或ChIP结合强度之间的统计关系;并且通过变量选择鉴定有影响的序列特征。我们研究了一些最先进的学习方法，包括逐步线性回归，多元自适应回归样条，神经网络，支持向量机，boosting和贝叶斯加性回归树（BART）。这些方法被应用到模拟数据集和两个全基因组ChIP芯片数据集上的TF Oct 4和Sox 2，分别在人类胚胎干细胞。我们发现，通过适当的学习方法，预测建模方法可以显着提高预测能力，并确定更多的生物学有趣的功能，如TF-TF相互作用，比PWM方法。特别是，BART和boosting在所有方法中表现出最好和最鲁棒的整体性能。
Predicting how and where proteins, especially transcription factors (TFs), interact with DNA is an important problem in biology. We present here a systematic study of predictive modeling approaches to the TF–DNA binding problem, which have been frequently shown to be more efficient than those methods only based on position-specific weight matrices (PWMs). In these approaches, a statistical relationship between genomic sequences and gene expression or ChIP-binding intensities is inferred through a regression framework; and influential sequence features are identified by variable selection. We examine a few state-of-the-art learning methods including stepwise linear regression, multivariate adaptive regression splines, neural networks, support vector machines, boosting and Bayesian additive regression trees (BART). These methods are applied to both simulated datasets and two whole-genome ChIP-chip datasets on the TFs Oct4 and Sox2, respectively, in human embryonic stem cells. We find that, with proper learning methods, predictive modeling approaches can significantly improve the predictive power and identify more biologically interesting features, such as TF–TF interactions, than the PWM approach. In particular, BART and boosting show the best and the most robust overall performance among all the methods.
登录
查看更多内容
影响因子：
14.9
作者：
Bulyk, ML;Johnson, PLF;Church, GM
通讯作者：
Church, GM
DOI：
10.1073/pnas.0407365101
发表时间：
2004-11-16
影响因子：
11.1
作者：
Das, D;Banerjee, N;Zhang, MQ
通讯作者：
Zhang, MQ
影响因子：
5.8
作者：
Hong, PY;Liu, XS;Wong, WH
通讯作者：
Wong, WH
影响因子：
21.3
作者：
Jiang, Jianming;Chan, Yun-Shen;Ng, Huck-Hui
通讯作者：
Ng, Huck-Hui
影响因子：
5.6
作者：
BERG, OG;VONHIPPEL, PH
通讯作者：
VONHIPPEL, PH